© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51189
    Prev
    Next
    INDEX
    Explanations

    Att

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chromatography
    -0.09
    termin
    -0.08
    .al
    -0.08
    Rw
    -0.08
    linen
    -0.08
    _RAW
    -0.07
    lden
    -0.07
    .raw
    -0.07
     Nis
    -0.07
     classe
    -0.07
    POSITIVE LOGITS
    acking
    0.10
     ake
    0.08
    พื้นที่
    0.08
    'instant
    0.08
    iebt
    0.08
    ygons
    0.08
    Boom
    0.08
    breng
    0.08
    Quantity
    0.07
     waho
    0.07
    Activations Density 0.000%

    No Known Activations